tag:blogger.com,1999:blog-3518334.post5975516349377898447..comments2024-02-26T03:12:14.514-07:00Comments on About Translation: Don’t worry: MT is not exactly perfect yetRiccardohttp://www.blogger.com/profile/08033214185364578008noreply@blogger.comBlogger7125tag:blogger.com,1999:blog-3518334.post-52245581322116742462011-12-06T07:42:47.164-07:002011-12-06T07:42:47.164-07:00Generally I think online dictionaries are very goo...Generally I think online dictionaries are very good for word translations. Of course there can always be mistakes in them and MT cannot know in which context the translation has to be made. I also don't think MT will ever replace human translation. However it will become more and important as one of many tools translators will use in future as well.Online Dictionaryhttp://hablaa.comnoreply@blogger.comtag:blogger.com,1999:blog-3518334.post-10799327512941138172011-10-25T09:46:16.245-06:002011-10-25T09:46:16.245-06:00Because language is full of exceptions and is extr...Because language is full of exceptions and is extremely ambiguous both at the lexical and at the syntactic level, machine will never be able to grasp the nuance. However,when the quality is not main concern machine translation can help us to get the gist of the translated text. So later we can decide if the information is valuable enough to be translated by human translator.Chinese Translationhttp://www.chinesetranslationpro.com/noreply@blogger.comtag:blogger.com,1999:blog-3518334.post-73060732913352494672011-10-25T06:26:21.830-06:002011-10-25T06:26:21.830-06:00Of course they don't. They are helpful in one ...Of course they don't. They are helpful in one way but harmful to quality of translation in the other way..Polish translatorhttp://www.fisz.co.uknoreply@blogger.comtag:blogger.com,1999:blog-3518334.post-71343482080193644682011-10-22T08:12:15.933-06:002011-10-22T08:12:15.933-06:00An interesting article: http://life.salon.com/2011...An interesting article: http://life.salon.com/2011/10/09/the_birth_of_the_google_translate_era/singleton/Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-3518334.post-27124852961344017102011-10-19T10:50:47.504-06:002011-10-19T10:50:47.504-06:00Hi Anna: Neither statistical nor rule-based MT sys...Hi Anna: Neither statistical nor rule-based MT system understand the text. And that's the whole point.Riccardohttps://www.blogger.com/profile/08033214185364578008noreply@blogger.comtag:blogger.com,1999:blog-3518334.post-30625627637662744412011-10-19T10:45:58.944-06:002011-10-19T10:45:58.944-06:00By definition, statistical MT systems like those p...By definition, statistical MT systems like those provided by Google and Bing are not meant to <i>understand</i> the text.Annanoreply@blogger.comtag:blogger.com,1999:blog-3518334.post-82314179068394988472011-10-19T03:59:18.591-06:002011-10-19T03:59:18.591-06:00Hi Riccardo
Thought I'd drop you a quick note...Hi Riccardo<br /><br />Thought I'd drop you a quick note on this. For MT to work, it needs to be customized per domain and if possible per client and even component. MS and Google are generic MT systems, so their results will fall short of what can be accomplished with more specific systems. There are a couple of open source MT systems that can be customized by the user: Apertium and Moses. I'll present on this in the ATA conference in Boston and be happy to discuss further if you are interested.<br /><br />That said, MT will not replace human translators. Rather, it will be used as a productivity tool. When combined properly with TM, it can give a great boost.<br /><br />Cheers,<br /><br />RubenRubénhttps://www.blogger.com/profile/14687860007052499787noreply@blogger.com